Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Transcription-specific terms

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "trans," likely related to transportation or transgender topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RANT
    -0.80
     Sunder
    -0.80
    mble
    -0.75
    FontSize
    -0.66
     maker
    -0.65
    FUL
    -0.63
     bent
    -0.63
     Cage
    -0.63
     jo
    -0.63
    awan
    -0.61
    POSITIVE LOGITS
    cend
    1.16
    gender
    1.12
    mission
    1.11
    parency
    1.06
    mitt
    1.06
    lator
    1.05
    missions
    1.02
    latable
    1.02
    portation
    1.00
    lucent
    0.99
    Act Density 0.017%

    No Known Activations